© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68923
    Prev
    Next
    INDEX
    Explanations

    the or a followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     at
    -2.30
     as
    -2.11
     after
    -2.02
     when
    -1.98
     during
    -1.89
     before
    -1.88
     had
    -1.87
     could
    -1.85
     with
    -1.82
     for
    -1.78
    POSITIVE LOGITS
    鵙
    2.00
     momentous
    1.92
     verhind
    1.92
     unbelievably
    1.92
     decidedly
    1.92
     ܙ
    1.91
     kompati
    1.88
     magnific
    1.83
     delightfully
    1.83
     wonderfully
    1.81
    Activations Density 0.079%

    No Known Activations